A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Automating look-ahead schedule generation for construction using linked-data based constraint checking and reinforcement learning
Abstract Look-ahead planning is the stage in construction planning where information from diverse sources is integrated and plans developed for the next six/eight weeks. Poor planning of construction site activities at this stage often results in cost overruns and schedule delays. This work presents a novel Look-Ahead Schedule (LAS) generation method, which uses reinforcement learning and linked-data based constraint checking within the reward, to address the issues associated with manual look-ahead planning and help construction professionals efficiently plan construction activities at this stage. Our proposal can generate conflict-free LAS significantly faster than conventional methods, demonstrating its capability as a decision support tool during look-ahead planning meetings. Therefore, this paper extends existing knowledge in the construction informatics domain by demonstrating the application of reinforcement learning to aid data-driven look-ahead planning.
Highlights This paper proposes a novel Look-Ahead Schedule (LAS) generation method. Proposed method combines Reinforcement Learning (RL) and Linked-Data based Constraint Checking (LDCC). Generates LAS automatically from codified information. Considers complex construction constraints distributed over multiple domains while generating LAS. A time-oriented RL using Q-Learning was used to model the LAS problem. Generate conflict-free LAS significantly faster than conventional methods. Acts as data-driven decision support system for look-ahead planning.
Automating look-ahead schedule generation for construction using linked-data based constraint checking and reinforcement learning
Abstract Look-ahead planning is the stage in construction planning where information from diverse sources is integrated and plans developed for the next six/eight weeks. Poor planning of construction site activities at this stage often results in cost overruns and schedule delays. This work presents a novel Look-Ahead Schedule (LAS) generation method, which uses reinforcement learning and linked-data based constraint checking within the reward, to address the issues associated with manual look-ahead planning and help construction professionals efficiently plan construction activities at this stage. Our proposal can generate conflict-free LAS significantly faster than conventional methods, demonstrating its capability as a decision support tool during look-ahead planning meetings. Therefore, this paper extends existing knowledge in the construction informatics domain by demonstrating the application of reinforcement learning to aid data-driven look-ahead planning.
Highlights This paper proposes a novel Look-Ahead Schedule (LAS) generation method. Proposed method combines Reinforcement Learning (RL) and Linked-Data based Constraint Checking (LDCC). Generates LAS automatically from codified information. Considers complex construction constraints distributed over multiple domains while generating LAS. A time-oriented RL using Q-Learning was used to model the LAS problem. Generate conflict-free LAS significantly faster than conventional methods. Acts as data-driven decision support system for look-ahead planning.
Automating look-ahead schedule generation for construction using linked-data based constraint checking and reinforcement learning
Soman, Ranjith K. (author) / Molina-Solana, Miguel (author)
2021-11-23
Article (Journal)
Electronic Resource
English
LAS , Look-ahead Schedule , RL , Reinforcement Learning , LDCC , Linked-data based Constraint Checking , SHACL , Shapes Constraint Language , RCPSP , Resource-Constrained Project Scheduling Problem , CPM , Critical Path Method , LPS , Last Planner System , CDE , Common Data Environment , RDF , Resource Description Framework , OWL , Web Ontology Language , GA , Genetic Algorithm , Look-ahead planning , Lean construction , Linked-data , Reinforcement learning , Scheduling , Resource constrained project scheduling problem (RCPSP) , Look ahead schedule (LAS) , Q-learning
Automating Schedule Review for Expressway Construction
| British Library Online Contents | 2005
Automating Schedule Review for Expressway Construction
| Online Contents | 2005
Automating Communication for Construction Schedule Control Using XML-based Information
| British Library Conference Proceedings | 2001